© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26095
    Prev
    Next
    INDEX
    Explanations

    scientific and research topics

    np_acts-logits-general · gemini-2.5-flash-lite

    words or phrases related to scientific or medical interactions, particularly in research contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron spotlights technical procedure and result terms—like “amputation,” “downgrad(e),” “interact(ions),” “time-dependent,” “identical,” and “boundary”—that name key experimental actions, measurements, or processes in scientific writing.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estampado
    -1.30
    ſty
    -1.23
     LEONARD
    -1.13
     egenskaper
    -1.11
     verhind
    -1.10
     jovens
    -1.09
     secado
    -1.09
    ₱
    -1.08
     hemsida
    -1.08
     ELIZABETH
    -1.07
    POSITIVE LOGITS
     other
    1.02
     end
    0.97
     ebenso
    0.93
    Наша
    0.92
     no
    0.91
    as
    0.90
     are
    0.90
    Affirm
    0.88
    龶
    0.87
     of
    0.87
    Activations Density 0.061%

    No Known Activations